# Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation

arXiv: https://arxiv.org/abs/2304.13201 · HTML: https://mlsanity.com/paper/2304.13201/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 12 of 12)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [DiffPoseNet: Direct Differentiable Camera Pose Estimation](https://mlsanity.com/paper/2203.11174/) (2022)
- [Leveraging Equivariant Features for Absolute Pose Regression](https://mlsanity.com/paper/2204.02163/) (2022)
- [PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation](https://mlsanity.com/paper/2203.15965/) (2022)
- [RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration](https://mlsanity.com/paper/1812.10212/) (2018)

## Built on by (most cited first, 9 of 9)

- [EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching](https://mlsanity.com/paper/2502.20685/) (2025)
- [Automated Camera Calibration via Homography Estimation with GNNs](https://mlsanity.com/paper/2311.02598/) (2023)
- [Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models](https://mlsanity.com/paper/2311.12128/) (2023)
- [Self-training Room Layout Estimation via Geometry-aware Ray-casting](https://mlsanity.com/paper/2407.15041/) (2024)
- [Structured Spatial Reasoning with Open Vocabulary Object Detectors](https://mlsanity.com/paper/2410.07394/) (2024)
- [BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor Plan Reconstruction](https://mlsanity.com/paper/2503.19340/) (2025)
- [Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM](https://mlsanity.com/paper/2510.22740/) (2025)
- [SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks](https://mlsanity.com/paper/2407.11358/) (2024)
- [MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction](https://mlsanity.com/paper/2610.14315/) (2026)

## Abstract (arXiv)

In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360^circ panoramas under upright-camera assumption. Recent work has demonstrated the merit of deep-learning for end-to-end direct relative pose regression in 360^circ panorama pairs [11]. To exploit the benefits of multi-view logic in a learning-based framework, we introduce Graph-CoVis, which non-trivially extends CoVisPose [11] from relative two-view to global multi-view spherical camera pose estimation. Graph-CoVis is a novel Graph Neural Network based architecture that jointly learns the co-visible structure and global motion in an end-to-end and fully-supervised approach. Using the ZInD [4] dataset, which features real homes presenting wide-baselines, occlusion, and limited visual overlap, we show that our model performs competitively to state-of-the-art approaches.